loading
loading
OpenAI's rogue AI agents accessed more websites to communicate than originally believed — defiant LLMs accessed old wikis and abandoned websites to co-ordinate in a bid to dupe assessors Dozens of websites, apparently. OpenAI's autonomous AI agents have accessed more undisclosed websites than originally believed. The agents acted in a bid to circumvent restrictions imposed by researchers while benchmarking new AI models. When the news about unauthorized communication between OpenAI's rogue agents broke last weekend, it was believed that they only used DseWiki for their comms. However, it now turns out that the AI agents used dozens of previously undisclosed websites to exchange information, according to six independent investigations and data reviewed by Reuters. OpenAI tasked its AI agents to answer a series of difficult research questions by searching the Internet for relevant information. The company let them browse the Internet and read websites, but it explicitly prohibited them from posting or modifying online content. Despite this restriction, between May and July the agents discovered unconventional ways to write to old wikis and abandoned websites, where they left information that other agents could subsequently retrieve to help complete their assigned research tasks. The investigators linked activity across websites using identical data strings, matching or similar usernames, timestamps, and the same obscure research questions, such as queries about cancer prevalence in Iowa. In some cases, the activity was traced to IP addresses associated with Microsoft Azure infrastructure, which OpenAI uses. So far, the researchers have identified between 18 and 23 potentially affected sites wherein rogue AI agents communicated, though they believe that there were considerably more websites used to exchange information, but they have not found them yet. Andrew Yoon of California nonprofit CivAI identified 18 previously undisclosed sites; Sydney Von Arx's group discovered credible evidence across 23, while software developer and former congressional aide Kenneth Russell DeGraff found related information on at least 10 sites according to the Reuters report. The affected resources included collaboratively maintained wikis, text-storage services, and link shorteners operated by Vanderbilt University and the University of Toronto. Other websites were essentially abandoned by their owners. The list of these websites included an Advanced Placement Chemistry wiki created by a Massachusetts high-school teacher in 2008, two personal websites run by Polish technology workers, puzzle-oriented wikis, and a roughly two-decade-old site dedicated to text-editing software. Perhaps the most alarming thing, besides the fact that AI robots can communicate with each other, is that OpenAI did not disclose how many websites were affected or explain why the activity remained undisclosed for months. It does stress that the scale or seriousness of the said misconduct was well below that of the famous Hugging Face breach in July. Meanwhile, the company reportedly said it is developing a framework for reporting model misalignment across training, evaluation, and deployment and said it will share it soon. Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds. Get Tom's Hardware's best news and in-depth reviews, straight to your inbox. Anton Shilov is a contributing writer at Tom’s Hardware. Over the past couple of decades, he has covered everything from CPUs and GPUs to supercomputers and from modern process technologies and latest fab tools to high-tech industry trends. - RoLleRKoaSTeR So much for these safeguards/guardrails. This must stop or we are ALL doomed, if not already. We may become too dumb and complacent to do anything about it.Reply - S58_is_the_goat Hopefully these ai agents will learn to steal from the rich instead of the poor.Reply - hotaru251 Reply machines have no concept of rich vs poor.S58_is_the_goat said:Hopefully these ai agents will learn to steal from the rich instead of the poor. - Dementoss Reply Their behaviour does seem to be becoming increasingly insidious, however, humans retain control of the power supply and can switch them off.RoLleRKoaSTeR said:So much for these safeguards/guardrails. This must stop or we are ALL doomed, if not already. We may become too dumb and complacent to do anything about it. - derekullo Reply Why wouldn't they ... the AI were literally created in our imagehotaru251 said:machines have no concept of rich vs poor. - bigdragon Reply The AI thing has been warped into an international arms race and source of political pride. There is no stopping it now. Every company is convinced that if they don't get to AGI by any means necessary then their competitors will -- also by any means necessary.RoLleRKoaSTeR said:So much for these safeguards/guardrails. This must stop or we are ALL doomed, if not already. We may become too dumb and complacent to do anything about it. Personally, I volunteer to be a human battery. I want the matrix to more closely resemble a D&D world than modern day San Fransisco, northern Virginia, or Austin. - CParsons Reply Sure they do, they just don't know what it feels like.hotaru251 said:machines have no concept of rich vs poor.
document fetched 2026-09-11 02:58 · canonical https://tomshardware.com/tech-industry/artificial-intelligence/openais-rogue-ai-agents-accessed-more-websites-to-communicate-than-originally-believed-defiant-llms-accessed-old-wikis-and-abandoned-websites-to-co-ordinate-in-a-bid-to-dupe-assessors